An AI-powered OCR skill designed to parse and extract structured data from academic degree certificates and diplomas.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install degree-certificate-ocr
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install degree-certificate-ocr using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Degree Certificate OCR skill is a high-performance optical character recognition tool designed to automate the extraction of key academic data from physical and digital diplomas. Powered by the Sugon-Scnet API, this skill allows developers and AI agents to parse credentials seamlessly, pulling critical fields such as the recipient's name, conferred degree type, granting institution, and graduation date.
By integrating this capability into Openclaw Skills, developers can build robust automation pipelines for HR screening, background checks, and academic verification. The skill eliminates manual data entry bottlenecks by translating unstructured document images (including JPG, PNG, and PDF formats) into highly reliable, structured JSON data.
DIPLOMA.SCNET_API_KEY credentials from the environment variables and sends an authorized request to the Sugon-Scnet OCR endpoint.Follow these steps to configure the Degree Certificate OCR capability within your Openclaw Skills workspace:
sc-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx.Create or edit your local environment file at config/.env:
# Sugon-Scnet OCR API Configuration
SCNET_API_KEY=your_scnet_api_key_here
SCNET_API_BASE=https://api.scnet.cn/api/llm/v1
Security Note: Never paste API keys directly into agent chat sessions.
Install the necessary Python dependencies via pip:
pip install requests
You can run the OCR skill directly from the CLI command line:
python .claude/skills/degree_certificate_ocr/scripts/main.py DIPLOMA /path/to/test.jpg
| Parameter | Type | Required | Description |
|---|---|---|---|
ocrType |
string | Yes | The type of document to identify. Must be DIPLOMA. |
filePath |
string | Yes | Absolute local file path to the target image or document. Supports jpg, png, and pdf formats. |
The output yields structured JSON containing recognized elements and confidence metrics:
{
"data": [
{
"result": [
{
"elements": {
"name": "Recipient Name",
"degree": "Type of Conferred Degree",
"institution": "Granting University/Institution",
"date": "Conferring Date"
},
"confidence": 0.98
}
]
}
]
}
429 Too Many Requests status codes to ensure high service availability.Loading
An AI-powered OCR skill that automates data extraction from vehicle license documents (both front and back pages) into structured JSON payloads.

A system utility designed to list, verify, and debug hardware microphones and audio input configurations for recording and transcription workflows.

An advanced OCR skill that extracts structured data, including names, majors, and credentials, from academic certificates using the Sugon-Scnet API.

An automated AI coding agent skill to extract structured data from marriage certificates using Sugon-Scnet OCR.

An intelligent labor law calculation router that automatically directs query topics to dedicated child agents for precise compensation and overtime computation.

An automated e-commerce procurement assistant bridging downstream store sales (Taobao/Douyin) with upstream 1688 suppliers.








































